Predicting

To address the downsides mentioned, this exploration paper presents a Personalized Career- path Recommender System( PCRS) to give guidance, and the right choice, and help all academy scholars choose their separate disciplines. The main idea of PCRS is to mimic the part of professional counsels who help scholars make this hard decision by assaying their academic and particular interests. The design of PCRS is grounded on a fuzzy-sense intelligence with two main input parameters; academic performance and specific profile.

[2] Prediction of student's academic performance using machine learning algorithms Learning analytics and supportive learning are known to be emerging research areas in today’s era of big data, data mining, machine learning, and artificial intelligence to facilitate students’ learning. Student education is crucial to the sustainable development of society as students learn knowledge from schools and through extracurricular activities and create abilities to contribute to the community. There are many students who have progressed to higher levels of education and earned degrees like Ph.D. while many graduate every year. However, there are some students who marginally pass the course and some who fail the course as well who are required to have a compulsory retake the same course. This paper has been proposed as an improvised conditional network-based deep support vector machine (ICGAN- DSVM) algorithm.ICGAN focuses on addressing the issue of low data volume that is using fewer datasets by mimicking new training datasets whereas DSVM extends SVM from shallow learning to deep learning. DSVM takes the advantage of a small dataset, as a key difference in comparing with the traditional deep neural network which makes it more efficient to work and execute.

[3] A Machine Learning Based Approach for Recommending Courses at Graduate Level Students often face confusion during their academic career regarding the choice of the courses they make and their future scope, hence they need proper guidance for the same which not everyone is accessible. This paper is used to propose a system that can be used for recommending courses to students according to their benefits and interests. The paper focuses on a higherlevel or graduate level of study. It utilizes techniques of Data Mining and Machine Learning in order to give accurate results to the students. The factors taken into account are based on the student's performance and their preferred interest and skills. Machine learning methods like neural networks and various learning algorithms can help in a student’s career and their best interest.

[4] Analysis Optimization K-Nearest Neighbor Algorithm with Certainty Factor in Determining Student Career A career is a series of development or progress in their respective professions experienced by every human being. These careers are manifested as a job title and job work and something related to the professional world and academic growth. The crucial element of a career is the development or progress on every level of life experienced by humans. K-Nearest Neighbour is a method for data. Classification and organization while the certainty factor is an uncertain decision-making method depicted in this paper. This study uses datasets like students’ interests, talents and exam scores to predict a career-appropriate decision for each student. The Student career prediction system was formed by combining two methods which are K-Nearest Neighborand the Certainty Factor. It was expected that the two-way analysis might provide a piece of better formation for students in determining their careers with accurate results. The KNearest Neighbor method received a value derived from the Certainty Factor which is apparently beneficial in predicting career prediction. A system was proposed that uses the KNN-certainty factor method to predict the student's career with accuracy.

[5] Analyzing the learning of individual and suggesting field of study using Machine Learning. The learning style can be defined as the way a student prefers to acquire, process, and retain the knowledge received from external sources. The prominent learning style classification model is called the VAK model. According to this theory visual, kinesthetic and auditory are the three major kinds of learning styles. Many kinds of research have shown that people prefer more than one way of learning and memorizing, hence categorizing a person as one of the above types as done in traditional methods is not reliable. A method that is used to identify learning styles more accurately is required. Machine learning is applied to achieve our aim in the most efficient way. Once we have accurate information about learning styles and methodologies, we can use it to suggest career options and predict outcomes. This research mainly aims at predicting the learning style combinations of students and suggesting a field of a domain using algorithms like kmeans, SVM, and decision tree.